BUG:357 BUG:380 fixes styling using css and movement of quick_help.html to top level.

scripts/mw2html_audacity/mw2html.py

@@ -51,6 +51,7 @@ config = None
 MOVE_HREF = 'movehref'
 MADE_BY_COMMENT = '<!-- Content generated by Mediawiki and mw2html -->'
 INDEX_HTML = 'index.html'
+QHELP_HTML = 'quick_help.html'
 url_filename_cache = {}
 redir_cache = {}
 wrote_file_set = set()
@@ -235,7 +236,6 @@ def pre_html_transform(doc, url):
     modified HTML document.
     """
     global config
-    new_urls = []
 
     if config.hack_skin:
         if config.skin == MONOBOOK_SKIN:
@@ -292,7 +292,7 @@ def pos_html_transform(doc, url):
         f.close()
 
     # add static dump time
-    footer_html = footer_text.replace('%DATE%', strftime("%Y-%m-%d %H:%M:%S"))
+    footer_html = footer_text.replace('%DATE%', strftime("%Y-%m-%d"))
 
     # add online url
     footer_html = footer_html.replace('%ONLINEURL%', url)
@@ -618,7 +618,9 @@ def url_to_filename(url):
         return url_filename_cache[nurl]
 
     #ParseResult(scheme='http', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html', params='', query='', fragment='')
-    L = list(urlparse.urlparse(nurl))
+    turl = re.sub(r'm/index.php\?title=', r'man/', nurl)
+    turl = re.sub(r'.css&[\S\s]+', r'.css', turl)
+    L = list(urlparse.urlparse(turl))
 
     #this way the url will not create a folder outside of the maindomain
     droot = get_domain(config.rooturl)
@@ -639,6 +641,10 @@ def url_to_filename(url):
             
     if lpath[-1]=='man':
         L[2] = INDEX_HTML
+    if lpath[-1].lower().startswith( 'quick_help'):
+        L[2] = QHELP_HTML
+        L[3] = ''
+        
        
 
     L[2] = L[2].strip('/')
@@ -824,6 +830,10 @@ def should_follow(url):
                 print url, 'is a file outside of scope with unknown extension'
             return False
 
+        # JKC: we do allow css from 'strange' places.
+        if '.css' in L[-1]:
+            return True
+        
         forbidden_parents = ['.php', '.html', '.htm']
         for fp in forbidden_parents:
             if fp in L[-1]:
@@ -852,7 +862,11 @@ def parse_html(doc, url):
     doc = doc.replace('-->', END_COMMENT_REPLACE)
 
     L = htmldata.urlextract(doc, url, 'text/html')
-
+    
+    # in this code we change each absolute url in L
+    # into a relative one.
+    # we also kick-off zillions of subthreads to collect 
+    # more pages.
     for item in L:
         u = item.url
         follow = should_follow(u)
@@ -868,7 +882,7 @@ def parse_html(doc, url):
             #  item.url = ''
             if config.debug:
                 print 'NOT INCLUDED     - ', u
-
+                
     newdoc = htmldata.urljoin(doc, L)
     newdoc = newdoc.replace(BEGIN_COMMENT_REPLACE, '<!--')
     newdoc = newdoc.replace(END_COMMENT_REPLACE, '-->')